Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    minority groups and rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.16
    п
    0.75
    트
    0.72
    ul
    0.72
    ม
    0.71
    ة
    0.70
     hyperparameters
    0.70
    И
    0.69
    мо
    0.69
    onics
    0.68
    POSITIVE LOGITS
    and
    1.37
    3
    1.30
    at
    1.14
    f
    0.98
    2
    0.93
    ៣
    0.92
    ள்ளதாக
    0.91
    a
    0.90
    4
    0.90
    ä
    0.89
    Act Density 0.001%

    No Known Activations